NewsEmbed: Modeling News through Pre-trained Document Representations

TL;DR

NewsEmbed is a novel multilingual document encoder trained on billions of automatically mined news articles, achieving strong performance on various NLP tasks with minimal human supervision.

Contribution

It introduces a contrastive and multi-label training approach for large-scale, multilingual news document representation with minimal supervision.

Findings

Outperforms existing models on multiple NLP tasks.

Provides billions of high-quality training examples.

Extends naturally to multilingual settings.

Abstract

Effectively modeling text-rich fresh content such as news articles at document-level is a challenging problem. To ensure a content-based model generalize well to a broad range of applications, it is critical to have a training dataset that is large beyond the scale of human labels while achieving desired quality. In this work, we address those two challenges by proposing a novel approach to mine semantically-relevant fresh documents, and their topic labels, with little human supervision. Meanwhile, we design a multitask model called NewsEmbed that alternatively trains a contrastive learning with a multi-label classification to derive a universal document encoder. We show that the proposed approach can provide billions of high quality organic training examples and can be naturally extended to multilingual setting where texts in different languages are encoded in the same semantic space. We experimentally demonstrate NewsEmbed's competitive performance across multiple natural language understanding tasks, both supervised and unsupervised.